upgrade_control_file

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing what each mode does: apply=false writes nothing, apply=true rewrites the file in place and preserves the original as <name>.bak. This destructive/backup behavior is exactly the kind of context annotations don't carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose and the workflow ordering, then enumerates return fields compactly. The return-value bullets are somewhat verbose but justified since there is no output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so, documenting fixes_available, diff, applied, and backup, plus the recommended follow-up loop with set_keyword and lint_control_file. Complete for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does thoroughly for apply (false = nothing written, true = in-place rewrite with .bak). The ctl parameter itself is not described, but its meaning is evident from the domain context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Bring a control file written for BPP 2.x/3.x up to current syntax') and clarifies its scope with the bpp-lint --diff/--fix mechanism. It is easily distinguishable from siblings like make_control_file and lint_control_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames the audience ('For users who arrive with an old control file') and prescribes the two-step workflow: call with apply=false first, show the diff, then apply=true only after agreement. It names set_keyword as the tool for the remaining manual fixes, though it does not explicitly rule out alternatives in a when-not sense.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.